A comparative assessment of time-consuming and laborious diatom analysis：Brief experimentation with suggestion of automatic identification.

Diatom testing is considered a useful method for providing supportive evidence for the diagnosis of drowning in forensic pathology. However, various factors remain controversial for recognizing diatoms, such as being time-consuming and laborious and influencing the consistency of the results. Given the absence of precise and well-defined studies on this subject, this study aimed to determine the relationship between the ability to identify diatoms and researchers with different technical backgrounds. A total of 55 samples from 18 cases, including water, lungs, liver, and kidneys, were treated using the microwave digestion-vacuum filtration-automated scanning electron microscopy (MD-VF-Auto SEM), which was used to compare diatom analyses among three groups of well-trained forensic pathologists (FPs), trained junior employees (JEs), and new trainees (TEs). In addition to achieving similar accuracy of positive findings from drowning cases, counting efficiency was evaluated based on taxonomy records and counting time after viewing more than 5500 diatom images. In contrast to the higher counting efficiency of the JE group than that of the TE group, we observed a statistically significant difference (p < 0.05) in the diatom classification between these two groups. Based on our experiments, an efficient analysis for automatically identifying and classifying diatoms is urgently required.

Detection of diatoms in a case of mud aspiration at a coastal area.

The source of diatoms detected in non-drowned bodies have been attributed to postmortem invasion, contamination during autopsy or diatom testing, or "natural load." However, sand aspiration has not been reported as a source. Herein, we report an autopsy case in which diatoms were detected in a non-drowned human who had aspirated mud. A man in his 60 s was found dead at a harbor park in Japan. His whole body was covered with sand, including his face. A situational investigation suggested that he may have entered the sea. Autopsy revealed intratracheal mud, with no obvious findings indicating drowning, suggesting that he died from mud aspiration probably due to hypothermia or non-lethal ethanol intoxication. In the diatom test, 10-100 diatoms/g were detected in bilateral lung samples, which were similar to those found in the intraoral and intratracheal mud and the sand samples from around the discovery site and not similar to those found in the seawater samples. The diatoms in the stomach content exhibited an intermediate trend between those found in the sand and seawater. Therefore, careful qualitative and quantitative analyses are required to differentiate between true drowning and false-positives in non-drowning cases to determine the cause of death.

Influence of the toxicological status on the diagnosis of fatal drowning.

Drowning is the leading cause of death by accident of everyday life in people under 25 years of age. Xenobiotics are frequently involved in drowning cases but their influence on the diagnosis of fatal drowning has not been studied so far. This preliminary study aimed to assess the influence of an alcohol and/or a drug intoxication on the autopsy signs of drowning, and on the results of diatom analyses in drowning deaths. Twenty-eight autopsy cases of drowning including 19 freshwater drownings, 6 seawater drownings, and 3 brackish water drownings were prospectively included. Toxicological and diatom tests were performed in each case. The influence of alcohol and other xenobiotics on drowning signs and diatom analyses was assessed separately then in combination through a global toxicological participation score (GTPS). Diatom analyses showed positive results in lung tissue in every case. No significant association was found between the degree of intoxication and the diatom concentration in the organs, even after considering freshwater drowning cases only. The vast majority of the traditional autopsy signs of drowning were not significantly affected by the individual toxicological status either, with the exception of lung weight which tended to raise in case of intoxication, probably due to the pulmonary edema and congestion increase. Further research on larger autopsy samples is needed to confirm the results of this exploratory study.

Relevance of diatom testing on closed organs of a drowned cadaver who died after receiving treatment for 10 days: A case report.

A male in his late adolescence fell into the sea and was found 50 min later with cardiopulmonary arrest. He was revived approximately 260 min after he drowned. Although he received several treatments, including venoarterial extracorporeal membrane oxygenation and continuous hemodiafiltration, he was clinically diagnosed with brain death. He died 10 days after the accident. The autopsy did not reveal any unremarkable findings other than those associated with post-resuscitation changes and medical treatment. The diatom test revealed 47.9, 311.6, and 577.5 diatom particles per gram from water, left lung, and right lung samples, respectively. No diatoms were detected in a 10 g liver sample, and 1 diatom was detected in each of approximately 12 g of bilateral kidney samples, which was different from the abundant species in the lung samples. The diatom test of the closed organs could be considered false negative for confirming drowning death since diatoms can also be detected in non-drowned cadavers on dry land. This suggests that diatoms might not reach the closed organs via circulation and that the diatom test of closed organ samples might no longer be necessary to confirm drowning deaths.

Conventional diatom testing using strong acid: (II) Number and types of diatoms detected in closed organs and lungs of 80 autopsy cases using only new Kjeldahl flasks.

The number of diatoms detected in the kidneys and liver varies considerably when comparing various reports, but the reason remains unclear. We previously showed that the reuse of Kjeldahl flasks is susceptible to generating false positives; false-positive results were observed in 17 of 60 tested flasks, and a maximum of 290 diatoms were detected. Furthermore, these data suggested that the number of diatoms in kidney and liver tissue may be much lower than previously thought. Therefore, only new Kjeldahl flasks were used to perform diatom tests on 80 autopsy cases (drowning and non-drowning victims) in this study. When combined with the 20 cases in a previous study, a total of 100 cases were analyzed. Four grams of lung, 10-30 g each of kidney and liver, 10 mL of blood, and 50-100 mL of water (discovery site) were examined. A large number of diatoms (n = 400) were found in organs other than the lungs in only 1 of 56 cases of suspected drowning (excluding cases of suspected drowning in baths). Together with the previous 20 cases, this single case represented only 1 of 76 cases (1.3 %). In closed organs and blood samples, 3 diatoms were found in 2 of 56 victims (3.6 %), and 1 or 2 diatoms were found in 8 victims (14 %). However, 5 diatoms were found in 1 of 10 bathtub drowning victims and 12 non-drowning victims (4.5 %), and 1 or 2 diatoms were found in 6 victims (27 %). Moreover, 1 or 2 diatoms were found in negative control flasks in 3 of 80 victims (3.8 %). The results showed that distinguishing false-positive results is difficult when a small number of diatoms are found in the kidneys and liver. Thus, the presence of diatoms in closed organs and blood seems to be unreliable as evidence of death by drowning, at least in the water environments in our region (freshwater areas: 23-26,000 diatoms/mL, median 200 diatoms; brackish water areas: 26-1200 diatoms/mL, median 210 diatoms; seawater area: 2-1000 diatoms/mL, median 24 diatoms). These results also reconfirmed that the reuse of flasks is the most important cause of false positives. Conversely, the presence of a large number of diatoms in lung samples (1-850,000 diatoms/g lung tissue; median (right lung): 440 diatoms, (left lung): 320 diatoms) is very informative and is an effective diagnostic aid in many cases.

An improved automated diatom detection method based on YOLOv5 framework and its preliminary study for taxonomy recognition in the forensic diatom test.

The diatom test is a forensic technique that can provide supportive evidence in the diagnosis of drowning but requires the laborious observation and counting of diatoms using a microscopy with too much effort, and therefore it is promising to introduce artificial intelligence (AI) to make the test process automatic. In this article, we propose an artificial intelligence solution based on the YOLOv5 framework for the automatic detection and recognition of the diatom genera. To evaluate the performance of this AI solution in different scenarios, we collected five lab-grown diatom genera and samples of some organic tissues from drowning cases to investigate the potential upper/lower limits of the capability in detecting the diatoms and recognizing their genera. Based on the study of the article, a recall score of 0.95 together with the corresponding precision score of 0.9 were achieved on the samples of the five lab-grown diatom genera via cross-validation, and the accuracy of the evaluation in the cases of kidney and liver is above 0.85 based on the precision and recall scores, which demonstrate the effectiveness of the AI solution to be used in drowning forensic routine.

Research Progress of Automatic Diatom Test by Artificial Intelligence.

Diatom test is the main laboratory test method in the diagnosis of drowning in forensic medicine. It plays an important role in differentiating the antemortem drowning from the postmortem drowning and inferring drowning site. Artificial intelligence (AI) automatic diatom test is a technological innovation in forensic drowning diagnosis which is based on morphological characteristics of diatom, the application of AI algorithm to automatic identification and classification of diatom in tissues and organs. This paper discusses the morphological diatom test methods and reviews the research progress of automatic diatom recognition and classification involving AI algorithms. AI deep learning algorithm can assist diatom testing to obtain objective, accurate, and efficient qualitative and quantitative analysis results, which is expected to become a new direction of diatom testing research in the drowning of forensic medicine in the future.

Comparison among Four Deep Learning Image Classification Algorithms in AI-based Diatom Test.

OBJECTIVES: To select four algorithms with relatively balanced complexity and accuracy among deep learning image classification algorithms for automatic diatom recognition, and to explore the most suitable classification algorithm for diatom recognition to provide data reference for automatic diatom testing research in forensic medicine. METHODS: The "diatom" and "background" small sample size data set (20 000 images) of digestive fluid smear of corpse lung tissue in water were built to train, validate and test four convolutional neural network (CNN) models, including VGG16, ResNet50, InceptionV3 and Inception-ResNet-V2. The receiver operating characteristic curve (ROC) of subjects and confusion matrixes were drawn, recall rate, precision rate, specificity, accuracy rate and F1 score were calculated, and the performance of each model was systematically evaluated. RESULTS: The InceptionV3 model achieved much better results than the other three models with a balanced recall rate of 89.80%, a precision rate of 92.58%. The VGG16 and Inception-ResNet-V2 had similar diatom recognition performance. Although the performance of diatom recall and precision detection could not be balanced, the recognition ability was acceptable. ResNet50 had the lowest diatom recognition performance, with a recall rate of 55.35%. In terms of feature extraction, the four models all extracted the features of diatom and background and mainly focused on diatom region as the main identification basis. CONCLUSIONS: Including the Inception-dependent model, which has stronger directivity and targeting in feature extraction of diatom. The InceptionV3 achieved the best performance on diatom identification and feature extraction compared to the other three models. The InceptionV3 is more suitable for daily forensic diatom examination.

Evaluation of Inspection Efficiency of Diatom Artificial Intelligence Search System Based on Scanning Electron Microscope.

OBJECTIVES: To explore the application values of diatom artificial intelligence (AI) search system in the diagnosis of drowning. METHODS: The liver and kidney tissues of 12 drowned corpses were taken and were performed with the diatom test, the view images were obtained by scanning electron microscopy (SEM). Diatom detection and forensic expert manual identification were carried out under the thresholds of 0.5, 0.7 and 0.9 of the diatom AI search system, respectively. Diatom recall rate, precision rate and image exclusion rate were used to detect and compare the efficiency of diatom AI search system. RESULTS: There was no statistical difference between the number of diatoms detected in the target marked by the diatom AI search system and the number of diatoms identified manually (P>0.05); the recall rates of the diatom AI search system were statistically different under different thresholds (P<0.05); the precision rates of the diatom AI system were statistically different under different thresholds(P<0.05), and the highest precision rate was 53.15%; the image exclusion rates of the diatom AI search system were statistically different under different thresholds (P<0.05), and the highest image exclusion rate was 99.72%. For the same sample, the time taken by the diatom AI search system to identify diatoms was only 1/7 of that of manual identification. CONCLUSIONS: Diatom AI search system has a good application prospect in drowning cases. Its automatic diatom search ability is equal to that of experienced forensic experts, and it can greatly reduce the workload of manual observation of images.

Construction and Application of YOLOv3-Based Diatom Identification Model of Scanning Electron Microscope Images.

OBJECTIVES: To construct a YOLOv3-based model for diatom identification in scanning electron microscope images, explore the application performance in practical cases and discuss the advantages of this model. METHODS: A total of 25 000 scanning electron microscopy images were collected at 1 500× as an initial image set, and input into the YOLOv3 network to train the identification model after experts' annotation and image processing. Diatom scanning electron microscopy images of lung, liver and kidney tissues taken from 8 drowning cases were identified by this model under the threshold of 0.4, 0.6 and 0.8 respectively, and were also identified by experts manually. The application performance of this model was evaluated through the recognition speed, recall rate and precision rate. RESULTS: The mean average precision of the model in the validation set and test set was 94.8% and 94.3%, respectively, and the average recall rate was 81.2% and 81.5%, respectively. The recognition speed of the model is more than 9 times faster than that of manual recognition. Under the threshold of 0.4, the mean recall rate and precision rate of diatoms in lung tissues were 89.6% and 87.8%, respectively. The overall recall rate in liver and kidney tissues was 100% and the precision rate was less than 5%. As the threshold increased, the recall rate in all tissues decreased and the precision rate increased. The F1 score of the model in lung tissues decreased with the increase of threshold, while the F1 score in liver and kidney tissues with the increase of threshold. CONCLUSIONS: The YOLOv3-based diatom electron microscope images automatic identification model works at a rapid speed and shows high recall rates in all tissues and high precision rates in lung tissues under an appropriate threshold. The identification model greatly reduces the workload of manual recognition, and has a good application prospect.

Effects of Digestive Temperature and Time on Diatom Test.

OBJECTIVES: To study the effects of temperature and time for diatoms digestion and find out suitable digestive temperature and time. METHODS: Eighty pieces of liver tissues were collected, each piece of tissue was 2 g, and 2 mL Pearl River water was added to each piece of tissue. The digestion temperature was set at 100 ℃, 120 ℃, 140 ℃, 160 ℃, 180 ℃ and the digestion time was set at 40, 50, 60, 70, 80 min. The liver tissue and water mixture were divided into 8 portions in each group. All the samples were tested by microwave digestive - vacuum filtration - automated scanning electron microscopy method. The quantity of diatom recovered and the quality of residue on the membrane were recorded. RESULTS: When the digestion time was set to 60 min, there were statistically significant differences in the number of diatoms recovered at different temperatures (P<0.05). The maximum number of diatoms recovered was (28 797.50±6 009.67) at 140 ℃, and the minimum residue was (0.60±0.28) mg at 180 ℃. When the digestion temperature was set at 140 ℃, there were statistically significant differences in the number of diatoms recovered at different digestion times (P<0.05). The number of diatoms recovered was the highest at 40 min, it was up to (20 650.88±1 950.29), and the residue quality of each group had no statistical significance among different digestion time groups(P>0.05). CONCLUSIONS: The effect of diatom digestion is related to temperature and time. When the digestion temperature was 140 ℃ and the digestion time was 40, 50 and 60 min, it is favorable for diatom test.

Change Rule of Diatom in Zhangweixin River in Dezhou.

OBJECTIVES: To study the annual variation of diatoms in Zhangweixin River, to provide theoretical support by using diatom examination to estimate the time and place of the corpse entering water, and to establish a diatom database. METHODS: Samples were taken from 4 sampling sites in Decheng section of Zhangweixin River for 12 consecutive months. Non-metric multi-dimensional scaling (NMDS) analysis was performed on the species and content of diatom samples. Based on the sampling site of Tianqu Road, Sprensen similarity coefficient analysis was conducted with the data of other 3 sites in Decheng section and Leling section of Zhangweixin River and Ningjin section in previous studies. RESULTS: The number of diatom species was positively correlated with diatom content. The average diatom content in different months ranged from 1 054 to 13 041/10 mL, and the species composition ranged from 8 to 16, with differences in dominant species. The similarity coefficient of diatom species within 2 km were all higher than 0.956 52, which could not be distinguished effectively. The similarity coefficients of Leling section and Ningjin section were 0.736 84 and 0.588 24 respectively, which could be effectively distinguished. CONCLUSIONS: The species and content of diatom vary in different months in Zhangweixin River, and the composition of diatom species is different in different basins, which can provide reference for estimating the time and place of the corpse entering water in the river.

Comparison of Application of MD-VF-Auto SEM Method and Plankton Gene Multiplex PCR System in the Diagnosis of Drowning.

OBJECTIVES: To compare the application effect of microwave digestion - vacuum filtration - automated scanning electron microscopy (MD-VF-Auto SEM) method and plankton gene multiplex PCR system in the diagnosis of drowning. METHODS: Lung, liver and kidney tissue of 10 non-drowning cases and 50 drowning cases were prepared for further MD-VF-Auto SEM method analysis and plankton gene multiplex PCR system analysis. The positive detection rate of the two methods in each tissue was calculated. RESULTS: The positive rate of the MD-VF-Auto SEM method detecting diatoms in drowning cases was 100%, and few diatoms were detected in the liver and kidney tissues of 6 non-drowning cases. By using the plankton gene multiplex PCR system, the diatom positive rate of drowning cases was 84%, and all the non-drowning cases were negative. There were significant differences in the positive rate of the liver, kidney tissues between MD-VF-Auto SEM method and plankton gene multiplex PCR system (P<0.05), as well as the total positive rate of cases. However, no significant differences were found in the positive rates of lung tissues (P>0.05). CONCLUSIONS: MD-VF-Auto SEM method is more sensitive than plankton gene multiplex PCR system in diatom test. But the plankton gene multiplex PCR system can also detect plankton other than diatoms. Combination of the two methods can provide a more reliable basis for the diagnosis of drowning.

Application of Diatoms Quantitative Analysis in the Diagnosis of Drowning.

OBJECTIVES: To retrospectively analyze diatom test cases of corpses in water and discuss the value of quantitative analysis of diatoms in the diagnosis of drowning. METHODS: A total of 490 cases of water-related death were collected. They were divided into drowning group and postmortem immersion group according to the cause of death. Diatoms in lung, liver, kidney tissue and water sample were analyzed quantitatively by microwave digestion-vacuum filtration-automated scanning electron microscopy (MD-VF-Auto SEM) method. The ratios of content of diatoms in lung tissue and water sample (CL/CD) were calculated. RESULTS: The results of diatom test for three organs (lung, liver and kidney) were all positive in 400 cases (85.5%); the content of diatom in lung, liver, kidney tissues, and water samples of drowning group were (113 235.9±317 868.1), (26.7±75.6), (23.3±52.2) and (12 113.3±21 760.0) cells/10 g, respectively; the species of diatom were (7.5±2.8), (2.6±1.9), (2.9±2.1) and (8.9±3.0) types, respectively; the CL/CD of drowning group and postmortem immersion group were (100.6±830.7) and (0.3±0.4), respectively. CONCLUSIONS: Quantitative analysis of diatoms can provide supportive evidence for the diagnosis of drowning, and the parameter CL/CD can be introduced into the analysis to make a more accurate diagnosis of drowning.

The effect of ethanol or long-time reaction on the diatom test in water samples using sodium hypochlorite.

BACKGROUND: The diatom test method using sodium hypochlorite (NaClO) was equivalent to the conventional method in water samples. However, the method using NaClO was inferior to the conventional method in lung samples, in which ethanol was used and the reaction with NaClO was longer compared with the method in water samples. Using water samples, we aimed to clarify whether these differences affect the diatom test result. MATERIALS AND METHODS: Thirteen water samples from natural water sources were each divided into four parts corresponding to four (2 × 2) digestion methods: 3 "digestion" vs. 1 "digestion" and with ethanol vs. without ethanol. After the base-2 logarithmic transformation, the diatom counts were analyzed using three-way analysis of variance (ANOVA); factor 1 was "digestion times," factor 2 was "ethanol," and factor 3 was "sample number," and the interaction between factors 1 and 2 was also analyzed. RESULTS: The geometric means of the diatoms from the 3 "digestion" with ethanol method, the 3 "digestion" without ethanol method, the 1 "digestion" with ethanol method, and the 1 "digestion" without ethanol method were 373.5, 551.8, 436.6, and 522.0, respectively. ANOVA showed a significant difference in factor 2 (P = 1.7 × 10-4). There was no significant difference in factor 1 (P = 0.46), and no significant interaction between factors 1 and 2 (P = 0.13). CONCLUSION: Ethanol may decrease the diatom count in the diatom test using NaClO. In contrast, the diatom frustules do not dissolve through three-times digestion using NaClO.

Conventional diatom testing using strong acid: Notable false-positive results caused by an underestimated contamination source (blind spot).

Low rates of diatom positivity in the closed organs of drowning victims present challenges for diatom testing. High positivity rates in closed organs of non-drowning victims also raise an important issue. These contradictory findings were common in diatom testing studies undertaken during the 1960-80 s, but the reasons remained unclear. In the present study, we identified one of the most important factors associated with false-positive results in diatom testing using strong acid. One to 290 false-positive diatoms were found in reused Kjeldahl flasks that were thoroughly washed after the first diatom testing and kept free of tissue before the second testing. False-positive results occurred in 11 of 20 cases when more than approximately 10,000 diatoms were present in digested tissue or water samples. Reused flasks were found to contain many common diatoms (<30 µm), including Cocconeis, Cymbella, Diatoma, Gomphonema, Navicula, and Nitzschia, in agreement with reports of diatoms identified in closed organs. Surprisingly, such false-positive results occurred even at the sixth diatom testing using the same flasks kept free of tissues in each analysis. In contrast, no diatoms were detected in any reagent or associated with other glassware. Thus, reuse of Kjeldahl flasks can readily cause false-positive results that cannot be completely prevented by cleaning the flasks using alkali detergents, as evidenced by detection of diatoms even after six tests. We assume that diatoms causing false-positive results are partially melted by heating and fixed onto the flask's inner surface glass, as the diatom frustule consists primarily of SiO2, similar to glass. Adherent diatoms are then released from the glass by re-heating at the next diatom testing. These results also suggest that the number of diatoms remaining in a flask can increase steadily as a result of repeated reuse for analysis of lung or water samples. In contrast, in analyses using only new flasks, only one or two diatoms were found in 4 of 20 kidney, 2 of 12 liver, and 2 of 8 blood samples from 20 drowning victims. It is difficult to determine whether such diatoms are actually carried via the blood circulation, as contamination with a few diatoms can occur during autopsy procedures and diatom testing. In conclusion, only new (unused) Kjeldahl flasks should be used for diatom testing with strong acid digestion. Moreover, these data suggest that the number and frequency of diatoms present in closed organs of drowning victims may be much lower than previously thought.

Evaluation of Inspection Efficiency of Diatom Artificial Intelligence Search System Based on Scanning Electron Microscope / 法医学杂志

OBJECTIVES@#To explore the application values of diatom artificial intelligence (AI) search system in the diagnosis of drowning.@*METHODS@#The liver and kidney tissues of 12 drowned corpses were taken and were performed with the diatom test, the view images were obtained by scanning electron microscopy (SEM). Diatom detection and forensic expert manual identification were carried out under the thresholds of 0.5, 0.7 and 0.9 of the diatom AI search system, respectively. Diatom recall rate, precision rate and image exclusion rate were used to detect and compare the efficiency of diatom AI search system.@*RESULTS@#There was no statistical difference between the number of diatoms detected in the target marked by the diatom AI search system and the number of diatoms identified manually (P>0.05); the recall rates of the diatom AI search system were statistically different under different thresholds (P<0.05); the precision rates of the diatom AI system were statistically different under different thresholds(P<0.05), and the highest precision rate was 53.15%; the image exclusion rates of the diatom AI search system were statistically different under different thresholds (P<0.05), and the highest image exclusion rate was 99.72%. For the same sample, the time taken by the diatom AI search system to identify diatoms was only 1/7 of that of manual identification.@*CONCLUSIONS@#Diatom AI search system has a good application prospect in drowning cases. Its automatic diatom search ability is equal to that of experienced forensic experts, and it can greatly reduce the workload of manual observation of images.

Comparison among Four Deep Learning Image Classification Algorithms in AI-based Diatom Test / 法医学杂志

OBJECTIVES@#To select four algorithms with relatively balanced complexity and accuracy among deep learning image classification algorithms for automatic diatom recognition, and to explore the most suitable classification algorithm for diatom recognition to provide data reference for automatic diatom testing research in forensic medicine.@*METHODS@#The "diatom" and "background" small sample size data set (20 000 images) of digestive fluid smear of corpse lung tissue in water were built to train, validate and test four convolutional neural network (CNN) models, including VGG16, ResNet50, InceptionV3 and Inception-ResNet-V2. The receiver operating characteristic curve (ROC) of subjects and confusion matrixes were drawn, recall rate, precision rate, specificity, accuracy rate and F1 score were calculated, and the performance of each model was systematically evaluated.@*RESULTS@#The InceptionV3 model achieved much better results than the other three models with a balanced recall rate of 89.80%, a precision rate of 92.58%. The VGG16 and Inception-ResNet-V2 had similar diatom recognition performance. Although the performance of diatom recall and precision detection could not be balanced, the recognition ability was acceptable. ResNet50 had the lowest diatom recognition performance, with a recall rate of 55.35%. In terms of feature extraction, the four models all extracted the features of diatom and background and mainly focused on diatom region as the main identification basis.@*CONCLUSIONS@#Including the Inception-dependent model, which has stronger directivity and targeting in feature extraction of diatom. The InceptionV3 achieved the best performance on diatom identification and feature extraction compared to the other three models. The InceptionV3 is more suitable for daily forensic diatom examination.

Research Progress of Automatic Diatom Test by Artificial Intelligence / 法医学杂志

Diatom test is the main laboratory test method in the diagnosis of drowning in forensic medicine. It plays an important role in differentiating the antemortem drowning from the postmortem drowning and inferring drowning site. Artificial intelligence (AI) automatic diatom test is a technological innovation in forensic drowning diagnosis which is based on morphological characteristics of diatom, the application of AI algorithm to automatic identification and classification of diatom in tissues and organs. This paper discusses the morphological diatom test methods and reviews the research progress of automatic diatom recognition and classification involving AI algorithms. AI deep learning algorithm can assist diatom testing to obtain objective, accurate, and efficient qualitative and quantitative analysis results, which is expected to become a new direction of diatom testing research in the drowning of forensic medicine in the future.

Comparison of Application of MD-VF-Auto SEM Method and Plankton Gene Multiplex PCR System in the Diagnosis of Drowning / 法医学杂志

OBJECTIVES@#To compare the application effect of microwave digestion - vacuum filtration - automated scanning electron microscopy (MD-VF-Auto SEM) method and plankton gene multiplex PCR system in the diagnosis of drowning.@*METHODS@#Lung, liver and kidney tissue of 10 non-drowning cases and 50 drowning cases were prepared for further MD-VF-Auto SEM method analysis and plankton gene multiplex PCR system analysis. The positive detection rate of the two methods in each tissue was calculated.@*RESULTS@#The positive rate of the MD-VF-Auto SEM method detecting diatoms in drowning cases was 100%, and few diatoms were detected in the liver and kidney tissues of 6 non-drowning cases. By using the plankton gene multiplex PCR system, the diatom positive rate of drowning cases was 84%, and all the non-drowning cases were negative. There were significant differences in the positive rate of the liver, kidney tissues between MD-VF-Auto SEM method and plankton gene multiplex PCR system (P<0.05), as well as the total positive rate of cases. However, no significant differences were found in the positive rates of lung tissues (P>0.05).@*CONCLUSIONS@#MD-VF-Auto SEM method is more sensitive than plankton gene multiplex PCR system in diatom test. But the plankton gene multiplex PCR system can also detect plankton other than diatoms. Combination of the two methods can provide a more reliable basis for the diagnosis of drowning.